Stars
RevIN: Reversible Instance Normalization For Accurate Time-series Forecasting Against Distribution Shift
Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai
python script to scrape screens from the screener.in website and export them to the excel file
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
allRank is a framework for training learning-to-rank neural models based on PyTorch.
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
Bayesian Structure Adaptation for Continual Learning. A non-parametric Bayesian approach on continual learning that learns the sparse deep substructure for each task by selecting weights to be used…
Question Answering models that can get an answer from Wikipedia pages and select a sentence subset as a reply to your question.
One weird trick for parallelizing convolutional neural networks
This project builds towards automatic summarisation of scientific papers
Online video stabilization using a novel MeshFlow motion model
predict short & long term rainfall
Kats, a kit to analyze time series data, a lightweight, easy-to-use, generalizable, and extendable framework to perform time series analysis, from understanding the key statistics and characteristi…
Sequence modeling benchmarks and temporal convolutional networks
TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.
PlaidML is a framework for making deep learning work everywhere.
A complete computer science study plan to become a software engineer.
cGAN-based Manga Colorization Using a Single Training Image.
freeCodeCamp.org's open-source codebase and curriculum. Learn to code for free.